Perplexity launches Multiagent: one lead can assign up to 16 agents across frontier models
Perplexity introduced Multiagent on November 17, 2026, a new effort setting for its Computer agent platform. A lead agent can assign up to 16 supporting agents across several frontier models, which share evidence and cross-check work before delivering one response.
Perplexity on November 17, 2026 introduced Multiagent, a new effort setting for its Computer agent platform. Under Multiagent, the lead agent can assign up to 16 supporting agents across several frontier models to analyze complex tasks, share evidence and cross-check their work before delivering a single response, according to Unite.AI's report.
What changed
Multiagent sits above Ultra in Computer's effort levels. Perplexity says it changes how information moves inside Computer's agent teams.
The company draws a contrast with Ultra. In Ultra, supporting agents report only to the lead. Multiagent is built so that agents work from shared evidence and check one another's output, rather than sending results to the lead alone.
Key details
- Product: Multiagent, an effort setting within Perplexity's Computer agent platform
- Announced: November 17, 2026
- Team size: a lead agent plus up to 16 supporting agents
- Models: several frontier models used across the agent team
- Output: a single response delivered after cross-checking
- Position: above the existing Ultra level
The report is based on a short summary of Perplexity's announcement. It does not name the specific models in the agent pool.
What this means
Multiagent is a change to how Computer organizes its agents, not a new trained model. The distinction Perplexity draws is in the communication structure: Ultra routes supporting agents' reports to the lead only, while Multiagent lets agents share evidence and cross-check each other's work before the lead returns one answer. Perplexity positions this setting for complex tasks, and it uses several frontier models within a single team rather than one.
Related Articles
Perplexity Brain Can Now Create and Update Agent Skills; 80,000+ Personal Skills Written for 20,000+ Users
Perplexity said on November 18, 2026, that Brain, the personalization system for its Computer agent, can now create and update reusable agent skills. According to the company, Brain wrote more than 80,000 personal skills for over 20,000 users between August 1, 2026, and November 14, 2026.
GitHub Copilot team customizations now generally available for organization teams
GitHub announced that team customizations for GitHub Copilot are generally available for organization teams. The feature lets teams share the Copilot plugins they rely on without asking every member to repeat the same setup.
Mistral launches Vibe Desktop for macOS and Windows, running parallel agent tasks locally or in the cloud
Mistral has released Vibe Desktop, a desktop app for its Vibe agent (formerly Le Chat), for macOS and Windows. It runs multiple tasks in parallel in a local repository or a cloud sandbox, and a Linux version is planned.
Gemini Notebook now builds interactive websites from your notes with a "make me a site" prompt
Google's Gemini Notebook, formerly known as NotebookLM, can now turn a notebook of research into an interactive website from a text description. TechRadar tested it on King Arthur research and got a finished site in about five minutes, though the reviewer says claims need checking against sources.
Comments
Loading...